Direct Prediction of BRAFV600E Mutation from Histopathological Images in Papillary Thyroid Carcinoma with a Deep Learning Workflow

Mutation BRAFV600E is highly specific for papillary thyroid carcinoma. It’s detected in 40-70% of all papillary thyroid carcinoma cases. Moreover this mutation is noticed in anaplastic carcinoma in 40-50%.This fact gives a chance to select patients and provide targeted therapy with multi-kinase inhibitors in cases of unresectable anaplastic carcinoma. The influence of BRAF V600E mutation for response to radioactive iodine therapy requires more evidence-based research. Existing methods for determining the BRAFV600E mutation have different accuracy, availability and cost. Other methodological aspects are also associated with the sample preparation of biological material, the quality of reagents, and the cross-validation of research results. In this review, on the basis of our own experience and literature data, the indications for determining the mutation of the BRAFV600E gene in clinical practice are refined, and a comprehensive comparative analysis of modern research methods has been conducted. This review is focused on a wide range of specialists of different types: oncologists, endocrinologists, radiologists, pathologists, and biologists.

Download Full-text

Classification of papillary thyroid carcinoma histological images based on deep learning

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-210100 ◽

2021 ◽

pp. 1-11

Author(s):

Yaning Liu ◽

Lin Han ◽

Hexiang Wang ◽

Bo Yin

Keyword(s):

Neural Network ◽

Differential Diagnosis ◽

Deep Learning ◽

Papillary Thyroid Carcinoma ◽

Thyroid Carcinoma ◽

Image Features ◽

Papillary Thyroid ◽

Histological Image ◽

Histological Images

Papillary thyroid carcinoma (PTC) is a common carcinoma in thyroid. As many benign thyroid nodules have the papillary structure which could easily be confused with PTC in morphology. Thus, pathologists have to take a lot of time on differential diagnosis of PTC besides personal diagnostic experience and there is no doubt that it is subjective and difficult to obtain consistency among observers. To address this issue, we applied deep learning to the differential diagnosis of PTC and proposed a histological image classification method for PTC based on the Inception Residual convolutional neural network (IRCNN) and support vector machine (SVM). First, in order to expand the dataset and solve the problem of histological image color inconsistency, a pre-processing module was constructed that included color transfer and mirror transform. Then, to alleviate overfitting of the deep learning model, we optimized the convolution neural network by combining Inception Network and Residual Network to extract image features. Finally, the SVM was trained via image features extracted by IRCNN to perform the classification task. Experimental results show effectiveness of the proposed method in the classification of PTC histological images.

Download Full-text

The ratio of BRAFV600E alleles can be used to assess the biological behavior of papillary thyroid carcinoma

10.1101/2020.10.31.20223610 ◽

2020 ◽

Author(s):

Dingcun Luo ◽

Yeqin Ni ◽

Shirong Zhang ◽

Yanping Xun ◽

Pan Zhao ◽

...

Keyword(s):

Papillary Thyroid Carcinoma ◽

Thyroid Carcinoma ◽

Tumor Recurrence ◽

Recurrence Risk ◽

Tumor Stage ◽

Biological Behavior ◽

Clinicopathological Parameters ◽

Quantitative Detection ◽

Papillary Thyroid ◽

Brafv600e Mutation

ABSTRACTBackgroundThe BRAFV600E mutations is an important molecular event in the occurrence and development of papillary thyroid carcinoma (PTC). A qualitative detection of the BRAFV600E mutation is still insufficient to explain the biological behavior of PTC. Though quantitative detection of the BRAFV600E mutation can reflect certain characteristics of PTC, its clinical value is still controversial. We aimed to investigate the association between the ratio of BRAFV600E alleles and clinicopathological parameters in PTC patients.MethodsGenomic DNA was extracted from specimens obtained from 329 PTC patients undergoing thyroidectomy. The ratio of BRAFV600E alleles was determined by amplification refractory mutation system (ARMS) and droplet digital polymerase chain reaction (ddPCR). Inconsistent results were further verified by next-generation sequencing (NGS). The clinicopathologic features, clinical tumor stage, and tumor recurrence risk stratification of all patients were correlated with the ratio of BRAFV600E alleles.ResultsThe sensitivity of ddPCR was superior to that of ARMS and almost the same as that of NGS. In total, 275 of 329 patients had the BRAFV600E mutation as determined by ARMS, ddPCR and NGS. The ratio of BRAFV600E alleles ranged from 0.17%-48.0%, with a median ratio of 12.58%, and significantly correlated with tumor size (p<0.001), capsule or extrathyroidal invasion (p<0.001), the number or rate of lymph node metastases (p<0.001), tumor stage (p=0.006) and tumor recurrence risk (p<0.001) but not with sex, age or multifocality. The ratio of BRAFV600E alleles was much lower in PTC patients with Hashimoto’s thyroiditis than in those without (p<0.001).ConclusionsThe ratio of BRAFV600E alleles can reliably reflect the biological behavior of PTC, making it a molecular-based stratification index of recurrence risk. The quantitative detection of BRAFV600E has the potential to guide the clinical diagnosis and treatment of PTC.

Download Full-text